Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Str
    -0.06
    bon
    -0.06
     pojist
    -0.06
    ektir
    -0.06
     endorse
    -0.06
     risen
    -0.06
    (best
    -0.06
     Line
    -0.06
     mentoring
    -0.06
    ubl
    -0.06
    POSITIVE LOGITS
    _smart
    0.07
    '\
    0.07
    ."_
    0.07
     ✔
    0.07
     prix
    0.06
     divisible
    0.06
    '_
    0.06
    abay
    0.06
    (util
    0.06
    ;-
    0.06
    Act Density 0.003%

    No Known Activations